Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    email addresses and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.15
     Dark
    -0.14
    irim
    -0.14
    urd
    -0.14
    eln
    -0.13
    eda
    -0.13
     Exped
    -0.13
    ange
    -0.13
    aval
    -0.13
    eration
    -0.13
    POSITIVE LOGITS
     protected
    0.34
    protected
    0.26
     Protected
    0.25
    Protected
    0.22
     protection
    0.17
    ä¿ĿæĬ¤
    0.17
    	protected
    0.17
     protecting
    0.16
     concealed
    0.15
     protective
    0.15
    Act Density 0.004%

    No Known Activations